NEURAL NETWORKS IN COMMUNICATIONS:ADMISSION CONTROL AND SWITCH CONTROL

摘要

We review recent papers on Neural Networks.and particularly two models which have found applications to communication network resource managemenL We then describe results from our ongoing work on the use of neural networks for call admission control and switch control.The call control problem is the selective admission of a set of calls from a number of inhomogeneous call classes,which may have widely differing characteristics.It is usually unknown in advance which combinations of calls can be simultaneously accepted so as to ensure satisfactory performance.The approach adopted here is that key network performance parameters are observed while carrying various combinations of calls.and theit relationship is learned by a neural network structure.The neural network model chosen has the ability to learn from the past-experienced results and to adapt to new and changing conditions.The switch control problem is the service policy used by a switch controller in transmiuing messages.In a crossbar switch with input queueing,significant loss of throughput can occur when head-of-line service is employed.Various alternatives to FIFO input queueing ale examined and their performance compared.We show how a neural network approach allows a policy to be implementcd which is optimal in an certain sense.